Runyard is a free hardware-aware AI model browser. You enter your CPU, GPU, and VRAM and it instantly shows every local LLM that will run on your machine, ranked by speed and quality.

How much VRAM do I need to run local LLMs?

8GB of VRAM runs 7B models like Llama 3.1 8B and Mistral 7B at Q4 quantization. 16GB unlocks 13B models. 24GB lets you run Mixtral 8x7B and Llama 3 70B at lower quantization.

What is the best local LLM for my GPU?

Use Runyard at www.runyard.dev — enter your GPU and VRAM and the Model Radar will rank every compatible LLM for your exact hardware, showing estimated tokens per second for each model.

Can I run Llama 3 locally?

Yes. Llama 3.1 8B at Q4 runs on any 8GB VRAM GPU. Llama 3.1 70B needs around 40GB VRAM at Q4, or an Apple Silicon Mac with 64GB+ unified memory.

Prompt Token Counter | Runyard Tools

P-12

Model size

Quantization

GPU or unified memory

System RAM

Context target

Quality preference

Speed preference

TurboQuant KV compression

Prompt text

Live result

15 tokens estimated

P-12

This prompt uses roughly 15 tokens, leaving about 8,177 tokens in a 8K window.

Prompt size

64 chars15 tokens

Planning estimate

Remaining context

8K8,177 left

Prompt budget check

How It Works

3 inputs. Instant results.

01

Set the scenario

Choose realistic hardware, model, and context assumptions.

02

Read the result

The hero shows a working result instead of a decorative promo block.

03

Act on the outcome

Use the result to adjust fit, speed, quantization, or context.

Features

Everything that powers prompt token counter.

01

Planning-first

Built to make local-AI decisions easier to reason about.

02

Local-AI focused

Built to make local-AI decisions easier to reason about.

03

Interactive hero

Built to make local-AI decisions easier to reason about.

04

Runyard design system

Built to make local-AI decisions easier to reason about.

05

Prompt text or document excerpt

Grounded in the actual inputs and outputs this page is designed around.

06

Estimated token usage

Grounded in the actual inputs and outputs this page is designed around.

07

Useful for prompt-heavy workflows

Grounded in the actual inputs and outputs this page is designed around.

08

Standalone tool

Grounded in the actual inputs and outputs this page is designed around.

Spotlight

The differentiator behind prompt token counter.

Typical paragraph

~130 words~180 tokens1.35× word count

One page of code

~500 lines~2000 tokensCode is token-dense

8K context usage

Unknown fit~6K prompt maxLeave 2K for reply

Visual comparison

Clarity

Fit

Actionability

Reading Results

How to read the output tiers.

Comfortable

<70%

Enough breathing room for normal use.

Tight

70%-95%

Should work, but overhead matters.

Borderline

95%-110%

Likely needs one tradeoff.

Too heavy

>110%

Time to step down.

Quick Reference

Common setups at useful defaults.

Scenario	Baseline	Result	Notes
Starter setup	7B / Q4 / 8K	Light local target	Good first benchmark
Balanced setup	8B / Q4 / 16K	Everyday sweet spot	Works for many users
Heavier setup	14B / Q5 / 16K	Quality-focused target	Needs stronger hardware
Stretch setup	32B / Q4 / 16K	Ambitious local target	Useful upper bound

* These are approximations for planning, not a promise of exact runtime behavior.

Benefits

Why people use prompt token counter.

01

Faster decisions

It helps eliminate dead-end local AI choices before you download, benchmark, or configure too much.

02

Clearer tradeoffs

The page turns a raw estimate into something you can actually act on.

03

Useful on its own

The hero provides a working tool surface while the rest of the page explains what the output means.

FAQ

Questions people ask before using prompt token counter.

What is a token in LLM terms?

A token is the basic unit of text in an LLM — roughly 0.75 words on average, though it varies by language and tokenizer. A typical paragraph is 100–200 tokens. Code is usually tokenized more coarsely than prose.

Why does counting tokens matter for local AI?

Local models have hard context limits. If a prompt exceeds the window it gets silently truncated, causing poor or confused responses. Knowing your token count lets you stay inside the limit with room for the reply.

How accurate is this token estimate?

The estimate uses a word-count approximation (words × 1.35). Real tokenization varies by model — Llama and GPT-family tokenizers differ. Treat these as planning estimates with roughly ±10% accuracy.

How much context should I leave for the model's reply?

A common practice is to leave 20–30% of the context window free for output. For an 8K window, keep prompts under 6K tokens. For coding where replies are long, leaving 30–40% is worth the discipline.

Does token count affect inference speed?

Not the input count alone, but context length does. A longer context means a larger KV cache, which slows each token generation step slightly. The effect compounds over long multi-turn conversations.

How do I reduce token usage without losing prompt meaning?

Remove filler phrases, switch to bullet points, summarise background context, and cut examples to the minimum needed. For RAG, retrieve only the most relevant chunks rather than full documents.

RUNYARD.DEV / Tools / Prompt Token Counter

Estimates on this page are directional and should be validated against your actual runtime and hardware.